Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2084 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3204. Min Range: -9.3204
Max Act: 9.3204. Min Act: -0.1700
Data Index: 4245693 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3204. Min Range: -9.3204
Max Act: 9.1954. Min Act: -0.1700
Data Index: 6038048 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3204. Min Range: -9.3204
Max Act: 9.0079. Min Act: -0.1700
Data Index: 3334176 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3204. Min Range: -9.3204
Max Act: 9.0079. Min Act: -0.1700
Data Index: 3362616 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3204. Min Range: -9.3204
Max Act: 9.0079. Min Act: -0.1700
Data Index: 4222423 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3204. Min Range: -9.3204
Max Act: 8.9454. Min Act: -0.1700
Data Index: 7666461 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3204. Min Range: -9.3204
Max Act: 8.9454. Min Act: -0.1700
Data Index: 7490507 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3204. Min Range: -9.3204
Max Act: 8.9454. Min Act: -0.1700
Data Index: 7509707 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3204. Min Range: -9.3204
Max Act: 8.8829. Min Act: -0.1700
Data Index: 613959 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3204. Min Range: -9.3204
Max Act: 8.8204. Min Act: -0.1700
Data Index: 8204593 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3204. Min Range: -9.3204
Max Act: 8.7579. Min Act: -0.1700
Data Index: 4245683 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3204. Min Range: -9.3204
Max Act: 8.6954. Min Act: -0.1700
Data Index: 6119777 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3204. Min Range: -9.3204
Max Act: 8.6954. Min Act: -0.1700
Data Index: 7328139 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3204. Min Range: -9.3204
Max Act: 8.6329. Min Act: -0.1700
Data Index: 1061285 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3204. Min Range: -9.3204
Max Act: 8.6329. Min Act: -0.1700
Data Index: 2318207 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3204. Min Range: -9.3204
Max Act: 8.5704. Min Act: -0.1700
Data Index: 2401116 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3204. Min Range: -9.3204
Max Act: 8.5704. Min Act: -0.1700
Data Index: 6202807 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3204. Min Range: -9.3204
Max Act: 8.5079. Min Act: -0.1700
Data Index: 272271 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3204. Min Range: -9.3204
Max Act: 8.5704. Min Act: -0.1700
Data Index: 4245685 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3204. Min Range: -9.3204
Max Act: 8.5079. Min Act: -0.1700
Data Index: 5909759 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19